microbert-uyghur-mx / README.md
lgessler's picture
Create README.md
4cdbb9d
metadata
language: uig
widget:
  - text: ھﺎﻳﺎﺗ ﺕﻮﻏﺭﻰﻗﻯڭﻥﻯڭ ﺉۆﻡۈﺭ ﻱﻰﻠﺗﻯﺯﻰﻧﻯ ﻕۇﺮﺘﺗەﻙ ﺉﺍۋﺎﻳﻼﭘ ﻱەﻲﻣەﻥ.

This is a MicroBERT model for Uyghur.

  • Its suffix is -mx, which means that it was pretrained using supervision from masked language modeling and XPOS tagging.
  • The unlabeled Uyghur data was taken from a February 2022 dump of Uyghur Wikipedia, totaling 2,401,445 tokens.
  • The UD treebank UD_Uyghur-UDT, v2.9, totaling 40,236 tokens, was used for labeled data.

Please see the repository and the paper for more details.